SubmissionNumber#=%=#163
FinalPaperTitle#=%=#MBZUAI-UNAM at SemEval-2024 Task 1: Sentence-CROBI, a Simple Cross-Bi-Encoder-Based Neural Network Architecture for Semantic Textual Relatedness
ShortPaperTitle#=%=#
NumberOfPages#=%=#9
CopyrightSigned#=%=#Jesus-German Ortiz-Barajas
JobTitle#==#
Organization#==#Mohamed bin Zayed University of Artificial Intelligence 
Masdar City, Abu Dhabi
Abstract#==#The Semantic Textual Relatedness (STR) shared task aims at detecting the degree of semantic relatedness between pairs of sentences on low-resource languages from Afroasiatic, Indoeuropean, Austronesian, Dravidian, and Nigercongo families. We use the Sentence-CROBI architecture to tackle this problem. The model is adapted from its original purpose of paraphrase detection to explore its capacities in a related task with limited resources and in multilingual and monolingual settings. Our approach combines the vector representation of cross-encoders and bi-encoders and possesses high adaptable capacity by combining several pre-trained models. Our system obtained good results on the low-resource languages of the dataset using a multilingual fine-tuning approach.
Author{1}{Firstname}#=%=#Jesus German
Author{1}{Lastname}#=%=#Ortiz Barajas
Author{1}{Username}#=%=#jgermanob
Author{1}{Email}#=%=#jesus.ortizbarajas@mbzuai.ac.ae
Author{1}{Affiliation}#=%=#Mohamed bin Zayed University of Artificial Intelligence
Author{2}{Firstname}#=%=#Gemma
Author{2}{Lastname}#=%=#Bel-Enguix
Author{2}{Email}#=%=#gbele@iingen.unam.mx
Author{2}{Affiliation}#=%=#Instituto de Ingeniería, Universidad Nacional Autónoma de México
Author{3}{Firstname}#=%=#Helena
Author{3}{Lastname}#=%=#Goméz-Adorno
Author{3}{Email}#=%=#helena.gomez@iimas.unam.mx
Author{3}{Affiliation}#=%=#IIMAS, Universidad Nacional Autónoma de México

==========
èéáğö